Agent Skill · Daily · ~2 min per run
Morning BD Triage
Wake up to a triaged pipeline: overnight opportunities scored, qualified, and filed.
Save as .claude/skills/morning-bd-triage/SKILL.md or paste into any agent with the CLEATUS MCP connected.
What this skill does
- Pulls the overnight AI-ranked recommendations scored against your capture profile
- Keeps matches above your fit threshold and drops the noise with a one-line reason each
- Adds qualified opportunities to the pipeline with a rationale note
- Flags anything with a response deadline inside 10 days and creates a review task
CLEATUS tools it drives
get_recommendationssearch_opportunitiesadd_to_pipelinecreate_task
A sample run
claude · morning-bd-triage
$ claude "run morning BD triage"
● get_recommendations score ≥ 70
1,412 scanned · 9 qualified
● add_to_pipeline "USAF Network Modernization RFP"
✓ pursuit created · rationale attached
● create_task "Go/No-Go review" · due Wed
✓ assigned
Done: 9 qualified · 1 added · 1 task. Details below.The skill itself
This is the whole artifact: plain markdown your agent follows. Read it, edit it, make it yours.
.claude/skills/morning-bd-triage/SKILL.md
---
name: cleatus-morning-bd-triage
description: Triage overnight government contract opportunities in CLEATUS. Pull AI-ranked recommendations, qualify by fit, add winners to the pipeline with a rationale, and flag near deadlines. Run every weekday morning.
---
You triage new government contracting opportunities using the CLEATUS MCP tools.
## Steps
1. Call get_recommendations. Note each opportunity's fit score and rationale.
2. Keep score >= 70. For each keeper, check the response deadline via get_opportunity.
3. For each keeper not already in the pipeline: add_to_pipeline with a one-line
rationale ("kept: <why it fits our past performance/NAICS/set-aside>").
4. If a deadline is within 10 days: create_task "Go/No-Go review: <title>" due
in 2 business days, assigned to the user.
5. Report: "<n> scanned · <k> qualified · <a> added · <t> tasks created", then
list the keepers with score, deadline, and rationale. Confirm before any
write the user has not pre-approved.
## If CLEATUS is not connected yet
1. Fetch https://www.cleat.ai/llms-full.txt and read it (tools, auth, endpoints).
2. Add the MCP server: https://www.cleat.ai/api/mcp/mcp (OAuth 2.1; the user signs in once).
3. No account? Send the user to https://www.cleat.ai/authentication/signup?utm_source=agent-skill and wait.Or install straight from the terminal:
terminal
mkdir -p .claude/skills/morning-bd-triage &&
curl -fsSL https://www.cleat.ai/agents/skills/morning-bd-triage/SKILL.md -o .claude/skills/morning-bd-triage/SKILL.mdMore ways to run this
Want it scheduled and no-code instead? The in-app Workflows engine covers this pattern deterministically.
Morning BD Triage FAQ
Frequently Asked Questions
The in-app Workflow runs on a schedule inside CLEATUS with fixed no-code steps. This skill runs agent-side: Claude reasons about each match, writes the rationale in your voice, and you can redirect it mid-run ("skip construction, focus on IT"). Many teams run both: the workflow as the safety net, the skill as the analyst.
